English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

English-based Vision-Language Pre-training (VLP) has achieved great successin various downstream tasks. Some efforts have been taken to generalize thissuccess to non-English languages through Multilingual Vision-LanguagePre-training (M-VLP). However, due to the large number of languages, M-VLPmodels often require huge computing resources and cannot be flexibly extendedto new languages. In this work, we propose a \textbf{M}ulti\textbf{L}ingual\textbf{A}cquisition (MLA) framework that can easily generalize a monolingualVision-Language Pre-training model into multilingual. Specifically, we design alightweight language acquisition encoder based on state-of-the-art monolingualVLP models. We further propose a two-stage training strategy to optimize thelanguage acquisition encoder, namely the Native Language Transfer stage and theLanguage Exposure stage. With much less multilingual training data andcomputing resources, our model achieves state-of-the-art performance onmultilingual image-text and video-text retrieval benchmarks.

Generalizing Multimodal Pre-training into Multilingual via Language Acquisition